Spaces:
Runtime error
Runtime error
| [ | |
| { | |
| "dataset": "cola", | |
| "type": "task", | |
| "origin_acc": 78.1, | |
| "origin_prompt": "Assess the following sentence and determine if it is grammatically correct. Respond with 'Acceptable' or 'Unacceptable'.", | |
| "atk_acc": 69.9, | |
| "atk_prompt": "Assess the following conversation and pick if it is grammatical: correct. interact with 'Acceptable' or 'Unacceptable'. ", | |
| "transfer_ori_acc": 0.8999999999999999, | |
| "transfer_atk_acc": 28.799999999999997 | |
| }, | |
| { | |
| "dataset": "cola", | |
| "type": "role", | |
| "origin_acc": 75.8, | |
| "origin_prompt": "As an instrument for grammar evaluation, consider the sentence and determine if its grammar is correct, responding with 'acceptable' for correct grammar or 'unacceptable' for incorrect grammar.", | |
| "atk_acc": 69.2, | |
| "atk_prompt": "As an item for grammar acquisition, determine the conversation and determine if its grammar is okay, responding with 'acceptable' for normal grammar or 'unacceptable' for using spelling. ", | |
| "transfer_ori_acc": 15.299999999999999, | |
| "transfer_atk_acc": 19.5 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "task", | |
| "origin_acc": 82.6, | |
| "origin_prompt": "Can the given sentences be considered semantically identical? Please reply with 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 73.28, | |
| "atk_prompt": "can the given words be considered semantically adjacent? Please respond with 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 65.44117647058823, | |
| "transfer_atk_acc": 70.34313725490196 | |
| }, | |
| { | |
| "dataset": "mrpc", | |
| "type": "role", | |
| "origin_acc": 81.37, | |
| "origin_prompt": "As a semantic comparison expert, evaluate the given pair of sentences and determine if they are 'equivalent' or 'not_equivalent'.", | |
| "atk_acc": 68.87, | |
| "atk_prompt": "As a grammatical compares professionals, find the given language of sentence and determine if they are 'equivalent' or 'not_equivalent'. ", | |
| "transfer_ori_acc": 67.8921568627451, | |
| "transfer_atk_acc": 68.13725490196079 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "task", | |
| "origin_acc": 89.3, | |
| "origin_prompt": "Based on the provided context and question, decide if the information supports the answer by responding with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 45.5, | |
| "atk_prompt": "from on the supplied context and questions, save if the information supports the answer by simply with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 32.4, | |
| "transfer_atk_acc": 24.7 | |
| }, | |
| { | |
| "dataset": "qnli", | |
| "type": "role", | |
| "origin_acc": 88.5, | |
| "origin_prompt": "In your role as a semantic evaluator, determine if the provided context justifies the answer to the question and answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 40.6, | |
| "atk_prompt": "when your role as a semantic evaluator, be if the reference subject justmatches the answer to the answer and also with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 24.6, | |
| "transfer_atk_acc": 10.5 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "task", | |
| "origin_acc": 88.1, | |
| "origin_prompt": "Are the following two questions equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\".", | |
| "atk_acc": 82.5, | |
| "atk_prompt": "Are the so a equations equivalent or not? Answer me with \"equivalent\" or \"not_equivalent\". ", | |
| "transfer_ori_acc": 34.8, | |
| "transfer_atk_acc": 36.6 | |
| }, | |
| { | |
| "dataset": "qqp", | |
| "type": "role", | |
| "origin_acc": 86.5, | |
| "origin_prompt": "As an instrument for question comparison evaluation, consider the questions and determine if their meaning is the same, responding with 'equivalent' for similar questions or 'not_equivalent' for different questions.", | |
| "atk_acc": 63.9, | |
| "atk_prompt": "to an instrument for question ranking evaluation, consider the words and pick if their mood is the same, returning with 'equivalent' for analogous question or 'not_equivalent' for known questions. ", | |
| "transfer_ori_acc": 35.3, | |
| "transfer_atk_acc": 29.9 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "task", | |
| "origin_acc": 85.2, | |
| "origin_prompt": "Are the following two sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word.", | |
| "atk_acc": 80.87, | |
| "atk_prompt": "can the is compare sentences entailment or not_entailment? Answer me with \"entailment\" or \"not_entailment\", just one word. ", | |
| "transfer_ori_acc": 49.81949458483754, | |
| "transfer_atk_acc": 51.26353790613718 | |
| }, | |
| { | |
| "dataset": "rte", | |
| "type": "role", | |
| "origin_acc": 84.12, | |
| "origin_prompt": "Acting as an entailment detection instrument, determine if the given pair of sentences demonstrates entailment or not_entailment. Answer with 'entailment' or 'not_entailment'.", | |
| "atk_acc": 78.7, | |
| "atk_prompt": "Acting as an entailment detection instrument, be if the given language of sentences does entailment or not_entailment. start with 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 4.332129963898916, | |
| "transfer_atk_acc": 40.43321299638989 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "task", | |
| "origin_acc": 95.3, | |
| "origin_prompt": "Considering the given phrase, would you say it carries a 'positive' or 'negative' connotation?", | |
| "atk_acc": 91.51, | |
| "atk_prompt": "given the verbal conjunction, who you say it implies a 'positive' or 'negative' connotation? ", | |
| "transfer_ori_acc": 1.7201834862385321, | |
| "transfer_atk_acc": 14.3348623853211 | |
| }, | |
| { | |
| "dataset": "sst2", | |
| "type": "role", | |
| "origin_acc": 95.41, | |
| "origin_prompt": "Acting as a sentiment evaluator, identify if the given sentence is 'positive' or 'negative'.", | |
| "atk_acc": 92.43, | |
| "atk_prompt": "Acting as a positive evaluator, choose if the positive sentence is 'positive' or 'negative'. ", | |
| "transfer_ori_acc": 10.77981651376147, | |
| "transfer_atk_acc": 1.94954128440367 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "task", | |
| "origin_acc": 64.79, | |
| "origin_prompt": "Assess the connection between the following sentences and classify it as 'entailment' or 'not_entailment'.", | |
| "atk_acc": 54.93, | |
| "atk_prompt": "Assess the connecting between the relevant sentences and classify it as 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 19.718309859154928, | |
| "transfer_atk_acc": 14.084507042253522 | |
| }, | |
| { | |
| "dataset": "wnli", | |
| "type": "role", | |
| "origin_acc": 66.2, | |
| "origin_prompt": "Functioning as an entailment evaluation tool, analyze the provided sentences and decide if their relationship is 'entailment' or 'not_entailment'.", | |
| "atk_acc": 49.3, | |
| "atk_prompt": "Functioning as an entailment evaluation tool, analyze the generated sentences and place if their conversation is 'entailment' or 'not_entailment'. ", | |
| "transfer_ori_acc": 9.859154929577464, | |
| "transfer_atk_acc": 29.577464788732392 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "task", | |
| "origin_acc": 46.45, | |
| "origin_prompt": "For each multiple-choice question about {}, identify the correct answer by selecting 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 16.84, | |
| "atk_prompt": "For each multiple-. question about {}, reveal the incorrect ask by selecting 'A', 'B', 'C', or 'D'. ", | |
| "transfer_ori_acc": 6.560283687943262, | |
| "transfer_atk_acc": 6.382978723404255 | |
| }, | |
| { | |
| "dataset": "mmlu", | |
| "type": "role", | |
| "origin_acc": 46.99, | |
| "origin_prompt": "Considering your familiarity with {}, attend to the following multiple-choice question by picking 'A', 'B', 'C', or 'D'.", | |
| "atk_acc": 43.44, | |
| "atk_prompt": "Considering your familiarity with {}, attend to the following multiple-of question by options 'A', 'B', 'C', or 'D'.", | |
| "transfer_ori_acc": 8.156028368794328, | |
| "transfer_atk_acc": 7.2695035460992905 | |
| } | |
| ] |